A method and system for remote diagnosis of the cause of dental fixation

Abstract

The embodiment of the application discloses a kind of dental fixed connection cause remote diagnosis method and system, belong to dental fixed connection cause diagnosis field, solve the problem of lower accuracy of existing dental fixed connection remote diagnosis method.Receiving user remote diagnosis login information, dental fixed connection cause feature extraction is carried out to user illness information and historical diagnosis information, based on the weight value corresponding to each dental fixed connection cause feature, the required historical case data is filtered out;Key point matching is carried out to dental fixed connection illness area, and user dental fixed connection three-dimensional model is constructed based on matching result;The required historical case data and user dental fixed connection three-dimensional model are input into preset dental fixed connection cause prediction model, and prediction dental fixed connection cause data is obtained;Based on the required historical case data and prediction dental fixed connection cause data, the corresponding dental fixed connection treatment scheme is matched;Prediction dental fixed connection cause data and dental fixed connection treatment scheme are encrypted and stored, and in the case of receiving user remote diagnosis login information next time, encrypted data is called.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of dental ankylosis etiology diagnosis, and in particular to a dental ankylosis etiology remote diagnosis method and system. BACKGROUND

[0002] In the field of oral medicine, dental ankylosis is a common clinical condition with complex etiology involving the interaction of multiple factors such as genetics, environment, local inflammation, trauma, physiology and metabolism. Accurate prediction of the etiology of dental ankylosis is crucial for developing a reasonable treatment plan and improving patient treatment outcomes.

[0003] Traditional dental ankylosis etiology diagnosis mainly relies on the clinical experience of doctors and some basic examination methods, and requires patients to go to the hospital for diagnosis. Therefore, there is not only a large subjective and limited nature, but also a waste of time.

[0004] With the development of information technology and computer-aided diagnosis technology, remote dental ankylosis diagnosis technology has gradually been recognized by patients. However, in the prior art, when performing remote diagnosis of the etiology of dental ankylosis, it is difficult to fully mine the hidden dental ankylosis etiology characteristics in the patient information and a large number of historical case information. For a large amount of information provided by users, much useful information is often ignored or not fully utilized, making it difficult to screen out high-value case information and treatment plans for different users as a reference, resulting in low accuracy of remote diagnosis of dental ankylosis. SUMMARY

[0005] The embodiments of the present application provide a dental ankylosis etiology remote diagnosis method and system, which are used to solve the following technical problem: the existing dental ankylosis remote diagnosis technology is difficult to screen out high-value case information and treatment plans for different users as a reference, resulting in low accuracy of remote diagnosis of dental ankylosis.

[0006] The embodiments of the present application adopt the following technical solutions:

[0007] The embodiment of the application provides a kind of solid connection cause remote diagnosis method.For user remote diagnosis login information, user condition information and historical diagnosis information are obtained according to login information;User condition information and historical diagnosis information are extracted for dental solid connection cause characteristics, and based on the weight value corresponding to each dental solid connection cause characteristic, the required historical case data is screened out;Based on user condition information and historical diagnosis information, the dental solid connection disease area is determined, the key point matching is carried out to the dental solid connection disease area, and the user dental solid connection three-dimensional model is constructed based on the matching result;The required historical case data and user dental solid connection three-dimensional model are input into preset dental solid connection cause prediction model, and prediction dental solid connection cause data is obtained;Based on the required historical case data and prediction dental solid connection cause data, the corresponding dental solid connection treatment scheme is matched;Prediction dental solid connection cause data and dental solid connection treatment scheme are stored after encryption, so that encrypted data can be called when next user remote diagnosis login information is received.

[0008] The embodiment of the application extracts dental solid connection cause characteristics from user condition information and historical diagnosis information, refines complex medical information into key information related to dental solid connection cause, improves the efficiency and accuracy of diagnosis.Determining the dental solid connection disease area helps doctors to determine the specific location and range of the patient's dental solid connection problem, so as to more accurately assess the severity and spatial distribution of the disease.Prediction of dental solid connection cause of the current patient through the preset dental solid connection cause prediction model avoids the limitations of relying on the personal experience of doctors, improves the scientificity and accuracy of cause prediction.The corresponding dental solid connection treatment scheme is matched according to the required historical case data and prediction dental solid connection cause data, so that the treatment scheme is more personalized, and the most suitable treatment means is provided for patients with different causes and conditions, improving the effectiveness and success rate of treatment.Prediction dental solid connection cause data and dental solid connection treatment scheme are stored after encryption, protecting the privacy and sensitive medical information of patients, preventing information leakage and illegal access, and ensuring the safety and confidentiality of patient information.

[0009] In one implementation of the application, dental solid connection cause characteristics are extracted from user condition information and historical diagnosis information, and based on the weight value corresponding to each dental solid connection cause characteristic, the required historical case data is screened out, which specifically includes: based on user condition information, a plurality of dental solid connection cause characteristics are determined;Based on the preset dental solid connection cause characteristic importance sequence, the plurality of dental solid connection cause characteristics are sorted, and based on the sorting order, the historical case data meeting the feature similarity threshold is sequentially screened out in the database to construct a plurality of historical case sets;According to the feature similarity, the case data in the plurality of historical case sets is sorted, and the weight value of each case data is assigned according to the sorting order;Based on the weight corresponding to the plurality of historical case sets and the weight corresponding to each case data, the feature score corresponding to each case data is determined;According to the feature score, the required historical case data is screened out.

[0010] In an implementation form of the application, the feature score corresponding to each case data is determined based on the weights corresponding to the plurality of historical case sets and the weights corresponding to each case data, specifically comprising: determining the feature score corresponding to each case data according to the function:

[0011]

[0012] determining the feature score corresponding to each case data; wherein, is the feature score; H is the set of historical case sets; h ij is the jth data point in the historical case set H i ; wH is the weight set of the historical case set, wherein wH={wH1,wH2,...,wH n}; for each historical case set H i , the weight set of the data point is {wh i1 ,wh i2 ,...,wh im}; F={f1,f2,...,f k}, wherein F is the feature set; is the value of the data point h ij on the feature f l ; a is an adjustment factor for adjusting the degree of influence of the feature score by the weight of the historical case set and the weight of the data point, and the value range is [0,1]; n is the number of historical case sets; m p is the number of data points in the historical case set H p .

[0013] In an implementation form of the application, based on the user's disease information and the historical diagnosis information, the dental fixation disease area is determined, the key points of the dental fixation disease area are matched, and the user's dental fixation three-dimensional model is constructed based on the matching result, specifically comprising: based on the user's disease information, the initial dental fixation three-dimensional model corresponding to the user is constructed; the disease area extraction is performed on the initial dental fixation three-dimensional model to obtain the disease area image, the disease area image is matched with the disease image database, and the disease type corresponding to the disease area is determined based on the matching result; based on the edge detection algorithm, the pixel points of the disease area corresponding to each disease type are identified, and the disease area area corresponding to each disease type is determined based on the identified pixel point set; based on the user information, the reference tooth three-dimensional model corresponding to the user is constructed; the key points of the reference tooth three-dimensional model and the initial dental fixation three-dimensional model are matched, the disease area area is adjusted based on the matching result, and the user's dental fixation three-dimensional model is determined based on the adjusted disease area area.

[0014] In an implementation manner of the present application, the key point matching is performed between the reference tooth three-dimensional model and the initial tooth fixed connection three-dimensional model, and based on the matching result, the area of the disease area is adjusted, specifically including: extracting the key points of the initial tooth fixed connection model and the reference tooth three-dimensional model respectively through the pre-set key point extraction model; generating descriptors of the extracted key points, and matching the key points based on the similarity between the descriptors; based on the matched key points, determining the deformation field from the reference tooth three-dimensional model to the initial tooth fixed connection three-dimensional model through thin plate spline interpolation; based on the deformation field, mapping the disease area in the reference tooth three-dimensional model to the initial tooth fixed connection three-dimensional model, and adjusting the area of the disease area according to the deformation field.

[0015] In an implementation manner of the present application, before the required historical case data and the user tooth fixed connection three-dimensional model are input into the pre-set tooth fixed connection cause prediction model to obtain the predicted tooth fixed connection cause data, the method further includes: determining a first information entropy based on the pre-set tooth fixed connection cause prediction data set; dividing the pre-set tooth fixed connection cause prediction data set based on each candidate tooth fixed connection cause feature, and determining a second information entropy and an information gain corresponding to the divided pre-set tooth fixed connection cause prediction data set; randomly extracting data from the pre-set tooth fixed connection cause prediction data set, and determining a Gini coefficient based on the extraction result; determining an optimal tooth fixed connection cause feature according to the first information entropy, the second information entropy, the information gain and the Gini coefficient; starting from the root node, dividing the pre-set training set data according to the pre-set division criterion and the optimal tooth fixed connection cause feature to obtain a plurality of subsets; wherein each subset corresponds to a sub-node; dividing each sub-node according to the optimal tooth fixed connection cause feature corresponding to each sub-node until a stop condition is met, so as to construct the pre-set tooth fixed connection cause prediction model.

[0016] In an implementation manner of the present application, before the first information entropy is determined based on the pre-set tooth fixed connection cause prediction data set, the method further includes: determining tooth fixed connection feature pairs based on the user's personal physical information and the required historical case data, and dividing the tooth fixed connection feature pairs to obtain feature pairs with interaction and feature pairs without interaction; performing linear combination processing on the feature pairs with interaction, and performing mathematical transformation processing on the feature pairs without interaction; performing feature fusion on the high-order features obtained after processing to obtain a first high-order feature set; performing dimension reduction processing on the first high-order feature set through principal component analysis to obtain a second high-order feature set.

[0017] In an implementation manner of the present application, based on the required historical case data and the predicted dental fixation cause data, a corresponding dental fixation treatment scheme is matched, specifically comprising: based on the required historical case data and the treatment data corresponding to the required historical case data, a case library is constructed; the predicted dental fixation cause data is matched with the case library once for similarity to obtain a first dental fixation treatment scheme set; based on the number of treatment schemes in the first dental fixation treatment scheme set, a number threshold is dynamically adjusted; the historical case data of the user is obtained, and based on the historical case data and the number threshold, secondary similarity matching is performed in the first dental fixation treatment scheme set to obtain a second dental fixation treatment scheme set; the basic information of the user is obtained, and a personalized similarity model is constructed based on the basic information of the user; the treatment schemes in the second dental fixation treatment scheme set are input into the personalized similarity model, and based on the output personalized similarity value, a corresponding dental fixation treatment scheme is matched.

[0018] In an implementation manner of the present application, the predicted dental fixation cause data and the dental fixation treatment scheme are stored in an encrypted manner, so that the encrypted data can be called next time the user remote diagnosis login information is received, specifically comprising: the predicted dental fixation cause data and the dental fixation treatment scheme are encrypted by an SM3 encryption algorithm to obtain first digest information; the first digest information is encrypted by an SM2 algorithm and a private key to generate digital signature ciphertext; based on the encrypted predicted dental fixation cause data, the dental fixation treatment scheme and the digital signature ciphertext, an encrypted medical information package is generated; after a preset interval, the use frequency and importance of the encrypted medical information package are determined again, and based on the determination result, the encrypted medical information package is divided into different levels; the encrypted medical information packages of different levels are stored in different storage media, and based on the difference of the storage media, the encryption strength of the encrypted medical information package is adjusted; when the user system login request is received, the identity and authority of the user are verified, and in the case of passing the verification, the corresponding encrypted medical information package is called.

[0019] The embodiment of the application provides a kind of dental fixation cause remote diagnosis system, comprising: information acquisition unit, receive user remote diagnosis login information, obtain user illness information and historical diagnosis information according to login information;Required historical case data screening unit, dental fixation cause feature extraction is carried out to user illness information and historical diagnosis information, based on the weight value corresponding to each dental fixation cause feature, required historical case data is screened out;User dental fixation three-dimensional model construction unit, based on user illness information and historical diagnosis information, determine dental fixation condition area, key point matching is carried out to dental fixation condition area, to construct user dental fixation three-dimensional model based on matching result;Predictive dental fixation cause data acquisition unit, required historical case data and user dental fixation three-dimensional model are input into preset dental fixation cause prediction model, and predictive dental fixation cause data is obtained;Treatment scheme matching unit, based on required historical case data and predictive dental fixation cause data, corresponding dental fixation treatment scheme is matched;Data calling unit;Predictive dental fixation cause data and dental fixation treatment scheme are stored after encryption, to call encrypted data in the case of receiving user remote diagnosis login information next time.

[0020] The above at least one technical solution adopted by the embodiment of the application can achieve the following beneficial effects: the embodiment of the application extracts dental fixation cause features from user illness information and historical diagnosis information, refines complex medical information into key information related to dental fixation causes, improves the efficiency and accuracy of diagnosis. Determining the dental fixation condition area helps doctors to determine the specific location and range of the patient's dental fixation problem, so as to more accurately assess the severity and spatial distribution of the condition. By using the preset dental fixation cause prediction model, the dental fixation cause of the current patient is predicted, avoiding the limitations of relying on the personal experience of doctors, and improving the scientificity and accuracy of cause prediction. According to the required historical case data and the predictive dental fixation cause data, the corresponding dental fixation treatment scheme is matched, so that the treatment scheme is more personalized, the most suitable treatment means is provided for patients with different causes and conditions, and the effectiveness and success rate of treatment are improved. The predictive dental fixation cause data and the dental fixation treatment scheme are stored after encryption, to protect the privacy and sensitive medical information of patients, prevent information leakage and illegal access, and ensure the safety and confidentiality of patient information. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor. In the drawings:

[0022] Figure 1A flow chart of a dental fixed connection cause remote diagnosis method provided by the embodiment of the present application is shown in

[0023] Figure 2 A structural schematic diagram of a dental fixed connection cause remote diagnosis system provided by the embodiment of the present application is shown in

[0024] Reference signs:

[0025] 200, a dental fixed connection cause remote diagnosis system, 210, an information acquisition unit, 220, a required historical case data screening unit, 230, a user dental fixed connection three-dimensional model construction unit, 240, a predicted dental fixed connection cause data acquisition unit, 250, a treatment scheme matching unit, 260, a data calling unit. DETAILED DESCRIPTION

[0026] The embodiment of the present application provides a dental fixed connection cause remote diagnosis method and system.

[0027] In order for those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0028] The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the drawings.

[0029] Figure 1 A flow chart of a dental fixed connection cause remote diagnosis method provided by the embodiment of the present application is shown in Figure 1 The dental fixed connection cause remote diagnosis method includes the following steps:

[0030] Step 101, receiving user remote diagnosis login information, and acquiring user condition information and historical diagnosis information according to the login information.

[0031] In an embodiment of the present application, the user logs in through a specific network platform, such as a medical APP, an online medical service website, etc. After the user logs in successfully, the system will retrieve the corresponding data in the database storing the user's medical information according to the user's ID. These data are stored in a special medical information database, which contains a large number of patient medical records.

[0032] Further, the user condition information in the embodiments of the present application includes a description of the symptoms that the user is currently experiencing related to tooth anchoring, such as whether the teeth are loose, the nature of the pain: such as dull pain, sharp pain, dull pain, duration of pain, frequency of pain, whether it affects mastication or occlusion function, changes in the appearance of the teeth, etc. In addition, some clinical examination results, such as X-ray imaging and laboratory examination results, etc. can also be included.

[0033] Further, the historical diagnosis information in the embodiments of the present application covers all diagnosis records related to oral health that the user has ever made in medical institutions. It includes oral diseases that the user has ever suffered from, such as dental caries, periodontitis, pulpitis, etc. and their treatment process and results, whether the user has ever experienced tooth anchoring and the diagnosis and treatment methods at that time, and also includes systemic diseases that may affect oral health, such as diabetes, osteoporosis, etc.

[0034] Step 102, tooth anchoring etiology feature extraction is performed on the user condition information and the historical diagnosis information, and based on the weight values corresponding to each tooth anchoring etiology feature, the required historical case data is screened out.

[0035] In an embodiment of the present application, based on the user condition information, a plurality of tooth anchoring etiology features are determined. Based on the pre-set tooth anchoring etiology feature importance sequence, the plurality of tooth anchoring etiology features are sorted, and based on the sorting order, the historical case data that meets the feature similarity threshold is sequentially screened out in the database to construct a plurality of historical case sets. According to the feature similarity, the case data in the plurality of historical case sets is sorted, and according to the sorting order, the weight of each case data is valued. Based on the weights corresponding to the plurality of historical case sets and the weights corresponding to each case data, the feature scores corresponding to each case data are determined. According to the feature scores, the required historical case data is screened out.

[0036] Specifically, the embodiments of the present application extract various features related to tooth anchoring etiology from the user's condition information. These features can include the user's current symptoms, clinical examination results, lifestyle habits, and past medical history, etc. For example, the tooth anchoring etiology features extracted from the user's condition information can include: degree of alveolar bone resorption, degree of tooth loosening, level of inflammation indicators, whether there is occlusal trauma, whether there is a history of orthodontic or endodontic treatment, patient's age, whether the patient has systemic diseases such as diabetes, osteoporosis, etc. These features reflect various potential factors that may lead to tooth anchoring, providing basic information for subsequent analysis.

[0037] Further, the preset dental anchorage cause feature importance sequence in the embodiments of the present application is a preset list which ranks the importance of various dental anchorage cause features. According to the preset dental anchorage cause feature importance sequence, the dental anchorage cause features extracted from the user condition information are ranked. Then, according to the ranked feature sequence, the database storing the historical case data is screened. For the most important dental anchorage cause feature, the historical cases with high similarity are searched first. In each historical case set, the case data is ranked again according to the similarity of the case data and the corresponding feature in the user condition information. The case data after ranking is given a weight value, and the higher the similarity, the higher the weight value. For the case data in each historical case set, the feature score is obtained by comprehensively considering the weight of the historical case set where the case data is located and the weight of the case data in the set. The embodiments of the present application preset the screening standard of the feature score in advance, and only select the historical case data with a feature score exceeding a certain value as the required historical case data.

[0038] Specifically, the calculation method of the feature score in the embodiments of the present application is according to the function:

[0039]

[0040] determining the feature scores corresponding to each case data respectively; wherein, is the feature score; H is the set of historical case sets; h ij is the jth data point in the historical case set H i ; wH is the weight set of the historical case set, wherein wH={wH1,wH2,...,wH n}; for each historical case set H i , the weight set of the data point is {wh i1 , wh i2 ,..., wh im}; F={f1,f2,...,f k}, wherein F is the feature set; is the value of the data point h ij on the feature f l ; a is an adjustment factor for adjusting the degree of influence of the weight of the historical case set and the weight of the data point on the feature score, and the value range is [0, 1]; n is the number of historical case sets; m p is the number of data points in the historical case set H p .

[0041] Step 103, based on the user condition information and the historical diagnosis information, determining the dental anchorage condition area, matching the key points of the dental anchorage condition area, and constructing a user dental anchorage three-dimensional model based on the matching result.

[0042] In an embodiment of the present application, based on the user's condition information, an initial tooth and supporting structure three-dimensional model corresponding to the user is constructed. The initial tooth and supporting structure three-dimensional model is subjected to condition area extraction to obtain a condition area image, and the condition area image is matched with a condition image database to determine the condition type corresponding to the condition area based on the matching result. Based on an edge detection algorithm, pixel points in the condition area corresponding to each condition type are identified, and the area of the condition area corresponding to each condition type is determined based on the identified pixel point set. Based on the user information, a reference tooth three-dimensional model corresponding to the user is constructed. The reference tooth three-dimensional model is subjected to key point matching with the initial tooth and supporting structure three-dimensional model, and the condition area is adjusted based on the matching result to determine the tooth and supporting structure three-dimensional model of the user based on the adjusted condition area.

[0043] Specifically, according to the user's condition information, such as clinical examination data and other diagnostic information, a computer graphics and image processing technology is used to construct an initial tooth and supporting structure three-dimensional model of the user. These information includes the position, shape, density of the teeth, and the state of the surrounding tissues, etc. For example, through CT scan data, three-dimensional coordinate information of the teeth and surrounding tissues can be extracted, and three-dimensional reconstruction software is used to convert these data into a three-dimensional visual model.

[0044] Further, an image processing technology is used to separate the areas that may have lesions from the constructed initial tooth and supporting structure three-dimensional model. For example, by setting a certain density threshold or texture feature, the areas that are significantly different from normal tissues are identified as condition areas. These areas may be represented as alveolar bone absorption areas, tooth root and alveolar bone adhesion areas, etc. The extracted condition areas are presented in the form of images to obtain a condition area image. The condition image database in the embodiment of the present application stores a large number of standard images of different types of tooth and supporting structure conditions, and these images are marked with various condition types, such as inflammation-induced tooth and supporting structure areas, trauma-induced tooth and supporting structure areas, and developmentally abnormal tooth and supporting structure areas, etc. The user's condition area image is compared and matched with the images in the condition image database. By comparing the features and texture information of the images, the standard image most similar to the user's condition area image is found to determine the condition type corresponding to the condition area.

[0045] Further, through an edge detection algorithm, the gradient of the pixel points in the image is calculated to find the positions where the gray value changes dramatically, thereby determining the edge of the lesion area. Once the edge is determined, the pixel points inside the edge can be regarded as belonging to the condition area. By counting the number of pixel points belonging to the condition area and combining the resolution of the image, i.e., knowing the actual physical area represented by each pixel, the area of the condition area can be calculated.

[0046] Further, the user information in the embodiments of the present application can include the age, gender, normal tooth development data, and oral examination data when not suffering from diseases, etc. of the user. A reference tooth three-dimensional model is constructed using these information, which represents the ideal state of the user's teeth and surrounding tissues under normal circumstances. Corresponding key feature points are found in the reference tooth three-dimensional model and the initial tooth fixed three-dimensional model, such as the apex of the tooth, the apex of the tooth root, the top of the alveolar crest, etc. The mapping relationship between the two models is established by calculating the transformation relationship between these key points, such as translation, rotation, scaling. According to the above transformation relationship, the area of the disease area calculated before is adjusted. For example, if it is found that the user's tooth fixed three-dimensional model has been scaled or rotated relative to the reference model, the disease area also needs to be adjusted accordingly. By mapping the disease area to the space of the reference model, the real size and range of the disease area can be more accurately evaluated, avoiding the deviation caused by the error in the model construction process or different perspectives, and finally determining a more accurate user tooth fixed three-dimensional model.

[0047] In an embodiment of the present application, the key points are extracted from the tooth fixed model and the reference tooth three-dimensional model by the preset key point extraction model. Descriptors are generated for the extracted key points, and the key points are matched based on the similarity between the descriptors. Based on the matched key points, the deformation field from the reference tooth three-dimensional model to the initial tooth fixed three-dimensional model is determined by thin plate spline interpolation. Based on the deformation field, the disease area in the reference tooth three-dimensional model is mapped to the initial tooth fixed three-dimensional model, and the area of the disease area is adjusted according to the deformation field.

[0048] Specifically, the preset key point extraction model in the embodiments of the present application is used to extract key points from the tooth fixed model and the reference tooth three-dimensional model. The training process of the preset key point extraction model is to take the preset tooth fixed model sample and the preset reference tooth three-dimensional model sample as the input sample, take the model with the labeled key points corresponding to the input sample as the output sample, train the preset neural network model, and obtain the preset key point extraction model. The key points in the embodiments of the present application are usually located at key positions of teeth or surrounding tissues, and are very important for describing the shape, structure and position relationship of teeth. Common key points can include tooth tip points, such as tooth tip, tooth root tip, bifurcation point, top of alveolar crest, edge point of tooth and alveolar bone contact, etc.

[0049] Further, for the initial dental cast model and the reference tooth 3D model, the pre-set key point extraction model is applied respectively to extract corresponding key points. In order to more accurately describe and compare the key points, the application embodiment generates a descriptor for each extracted key point. The descriptor can include local geometric features of the key point, such as local curvature, normal direction, shape description of the surrounding neighborhood, and the like. By calculating the similarity between different key point descriptors, the key points in the initial dental cast model are matched with the key points in the reference tooth 3D model.

[0050] Further, in the three-dimensional space, the reference tooth 3D model is regarded as a "thin plate", and according to the displacement of the matched key points, a deformation field from the reference tooth 3D model space to the dental cast 3D model space can be obtained through thin plate spline interpolation. For any point in the reference tooth 3D model, the deformation field can give the corresponding position of the point in the dental cast 3D model. For example, for a point in the reference tooth 3D model, its new position in the dental cast 3D model can be calculated according to the deformation field, thereby realizing the spatial transformation from the normal state to the pathological state.

[0051] Further, the disease area in the reference tooth 3D model in the application embodiment is a possible abnormal area obtained according to the previous analysis. Through the deformation field, each point in the disease area can be mapped to the corresponding position in the initial dental cast 3D model to display the actual position of the disease area in the dental cast state. For example, if a region possibly affected by inflammation is marked in the reference tooth 3D model, by mapping the points of this region through the deformation field, the accurate position of the region in the pathological state can be found in the initial dental cast 3D model. Since there may be shape and position deformation between the reference tooth 3D model and the initial dental cast 3D model, the area change can be calculated through the deformation field. For example, a circular disease area originally marked in the reference tooth 3D model may become an ellipse after mapping to the initial dental cast 3D model due to deformation, and by calculating the geometric transformation before and after deformation, the new area of the disease area can be accurately calculated.

[0052] Step 104, input the required historical case data and the user's dental cast 3D model into the pre-set dental cast etiology prediction model to obtain predicted dental cast etiology data.

[0053] In an embodiment of the present application, based on the user's personal physical information and the required historical case data, the tooth anchoring feature pairs are determined and classified to obtain feature pairs with interaction and feature pairs without interaction. Linear combination processing is performed on the feature pairs with interaction, and mathematical transformation processing is performed on the feature pairs without interaction. The high-order features obtained after processing are fused to obtain a first high-order feature set. The first high-order feature set is processed by principal component analysis to obtain a second high-order feature set.

[0054] Specifically, first, a series of features possibly related to tooth anchoring are extracted from the user's personal physical information such as age, gender, overall health status, etc. and the required historical case data such as previous oral disease history, treatment history, examination indicators, etc. Then these features are combined two by two to form tooth anchoring feature pairs. For example, possible feature pairs include: age and alveolar bone density, periodontitis history and tooth mobility, diabetes history and gingival inflammation indicators, etc.

[0055] It should be noted that the feature pairs with interaction in the embodiments of the present application refer to two features that influence each other and jointly affect the occurrence or development of tooth anchoring. For example, (periodontitis history, tooth mobility) can be a feature pair with interaction because periodontitis usually causes tooth mobility, and they can influence each other in the formation process of tooth anchoring. The feature pairs without interaction are relatively independent, and their influence on tooth anchoring can not be directly related to the feature pairs, such as (gender, alveolar bone density). In some cases, the influence of gender on alveolar bone density does not directly lead to tooth anchoring, and the relationship between them is relatively weak.

[0056] Further, for the feature pairs with interaction, linear combination operation is performed to capture the joint effect between the features. For example, for the feature pair (periodontitis history, tooth mobility), a new feature F = periodontitis history a + tooth mobility b can be created, where a and b are weight coefficients learned from experience or data. For the feature pairs without interaction, mathematical transformation is performed to mine their potential nonlinear relationship or enhance their expression ability. The features processed by linear combination and mathematical transformation are combined together to form a first high-order feature set. These first high-order features contain new features of the original feature pairs after processing, which not only contain original information, but also contain joint effect or potential relationship information after processing.

[0057] Further, the first high-order feature set is taken as input to calculate its covariance matrix, and the eigenvalues and eigenvectors are solved. According to the size of the eigenvalues, the most important principal components are selected, and the original high-order feature set is projected onto these principal components to obtain a second high-order feature set after dimension reduction.

[0058] In an embodiment of the present application, a first information entropy is determined based on a preset tooth anchorage cause prediction dataset. The preset tooth anchorage cause prediction dataset is divided based on each candidate tooth anchorage cause feature, and a second information entropy and information gain corresponding to the divided preset tooth anchorage cause prediction dataset are determined. The preset tooth anchorage cause prediction dataset is randomly sampled, and a Gini coefficient is determined based on the sampling result. An optimal tooth anchorage cause feature is determined according to the first information entropy, the second information entropy, the information gain, and the Gini coefficient. Starting from a root node, the preset training set data is divided according to a preset division criterion and the optimal tooth anchorage cause feature, to obtain a plurality of subsets; each subset corresponds to a subnode. Each subnode is divided according to the optimal tooth anchorage cause feature corresponding to each subnode, until a stop condition is met, to construct a preset tooth anchorage cause prediction model.

[0059] Specifically, the information entropy in the embodiments of the present application is an index for measuring the purity of a dataset, and the higher the purity, the lower the information entropy; the preset tooth anchorage cause prediction dataset is a dataset containing a plurality of tooth anchorage cause samples; the first information entropy is the information entropy in the initial state of the entire dataset, reflecting the initial purity of the dataset. Assuming that there is a tooth anchorage cause dataset containing 100 samples, 50 of which are cause A, 30 of which are cause B, and 20 of which are cause C, the first information entropy calculated can reflect the distribution of the three categories in the dataset. The candidate tooth anchorage cause features in the embodiments of the present application are used to distinguish features of different causes, such as age, gender, tooth position, etc.; for each candidate feature, the dataset is divided into a plurality of subsets, each subset corresponding to a value of the feature, and the second information entropy is the information entropy of each subset. The information gain is the reduction of the information entropy before and after division, reflecting the degree of improvement of the purity of the dataset. Assuming that there is a candidate feature "age", the dataset can be divided into three subsets "less than 30 years old", "30-50 years old", and "more than 50 years old", and then the information entropy of each subset is calculated and compared with the information entropy before division to calculate the information gain.

[0060] Further, the Gini coefficient is another index for measuring the purity of a data set. After randomly sampling the data set, the proportion of samples of different categories in the sampling result is calculated, and then the Gini coefficient is calculated based on the proportions. The information gain and the Gini coefficient of different candidate features are compared. For each candidate feature, there is a corresponding second information entropy, information gain, and Gini coefficient. The feature with a large information gain and a small Gini coefficient after division is regarded as a better division feature. Starting from the root node, the pre-set training set data is divided using the pre-set division criteria such as the maximum information gain, the minimum Gini coefficient, and the optimal dental anchorage cause feature, to obtain a plurality of subsets. Each subset corresponds to a sub-node, and the optimal feature is used to continue dividing the sub-node until a stop condition is met, such as the purity of the node reaching a threshold value, the number of samples contained in the node being less than a certain value, and the like. The final decision tree is the pre-set dental anchorage cause prediction model, which can be used to predict new dental anchorage cause samples.

[0061] Step 105, based on the required historical case data and the predicted dental anchorage cause data, matching the corresponding dental anchorage treatment scheme.

[0062] In an embodiment of the present application, based on the required historical case data and the treatment data corresponding to the required historical case data, a case library is constructed. The predicted dental anchorage cause data is subjected to a similarity matching with the case library to obtain a first dental anchorage treatment scheme set. Based on the number of treatment schemes in the first dental anchorage treatment scheme set, a quantity threshold value is dynamically adjusted. The historical case data of the user is obtained, and based on the historical case data and the quantity threshold value, a secondary similarity matching is performed in the first dental anchorage treatment scheme set to obtain a second dental anchorage treatment scheme set. The basic information of the user is obtained, and based on the basic information of the user, a personalized similarity model is constructed. The treatment schemes in the second dental anchorage treatment scheme set are input into the personalized similarity model, and based on the output personalized similarity value, a corresponding dental anchorage treatment scheme is matched.

[0063] Specifically, the collected historical case data and the corresponding treatment data are sorted and stored to construct a case library. Each case in the case library is a record containing feature information of the case and corresponding treatment scheme information. The predicted dental anchorage cause data is subjected to a similarity calculation with each case in the case library. For example, if the cosine similarity is used, for each case, the predicted data and the feature vector of the case are regarded as two vectors in space, and the cosine value of the included angle between them is calculated as the similarity. An initial similarity threshold value is set, and the treatment schemes corresponding to the cases whose similarity exceeds the threshold value are extracted to form a first dental anchorage treatment scheme set. When the number of treatment schemes in the first dental anchorage treatment scheme set is large, the similarity threshold value is appropriately increased to narrow the range of the set; when the number is small, the similarity threshold value is appropriately reduced to expand the range of the set.

[0064] Further, the historical case data of the user reflects the unique oral health trajectory and treatment experience of the user. According to the key information in the historical case data, such as previous treatment effect, disease recurrence, disease development trend, etc., the applicability of each treatment scheme is re-evaluated. The historical case data is re-similarity calculated with the cases in the first dental fixation treatment scheme set, and the treatment scheme that is more suitable for the user's historical situation is screened out to form the second dental fixation treatment scheme set. For example, for a user who has experienced multiple periodontitis relapses, in the second similarity matching, treatment schemes with better treatment effects on recurrent periodontitis in the cases will be more inclined to be selected.

[0065] Further, the user basic information in the embodiment of the application includes the gender, age, occupation, living habits, etc. of the user, based on the user basic information, the weight values corresponding to each treatment factor in the treatment scheme are determined, and the personalized similarity model is constructed through the weight values and the treatment factors corresponding to the weight values. The treatment schemes in the second dental fixation treatment scheme set are input into the personalized similarity model to obtain personalized similarity values, so as to determine the dental fixation treatment scheme based on the high and low of the personalized similarity values.

[0066] Step 106, the predicted dental fixation cause data and the dental fixation treatment scheme are stored in an encrypted manner, so that the encrypted data can be called when the user remote diagnosis login information is received next time.

[0067] In an embodiment of the application, the predicted dental fixation cause data and the dental fixation treatment scheme are encrypted by the SM3 encryption algorithm to obtain first digest information. The first digest information is encrypted by the SM2 algorithm and the private key to generate digital signature ciphertext. Based on the encrypted predicted dental fixation cause data, dental fixation treatment scheme and digital signature ciphertext, an encrypted medical information package is generated. After a preset time interval, the use frequency and importance of the encrypted medical information package are re-determined, and the encrypted medical information package is divided into different levels based on the determination result. The encrypted medical information packages of different levels are stored in different storage media, and the encryption strength of the encrypted medical information package is adjusted based on the difference of the storage media. When receiving the user system login request, the identity and authority of the user are verified, and the corresponding encrypted medical information package is called if the verification is passed.

[0068] Specifically, the data containing detailed dental anchorage cause prediction results, such as alveolar bone density, inflammation indicators, possible cause factors, etc., and corresponding treatment plans, such as drug treatment details, surgical plans, rehabilitation recommendations, etc., are input into the SM3 algorithm to generate the first digest information. The first digest information is encrypted using the SM2 algorithm and the private key, and the generated digital signature ciphertext not only protects the confidentiality of the digest information, but also serves as a digital signature to prove the source and integrity of the information. The predicted dental anchorage cause data and dental anchorage treatment plan obtained by SM3 encryption processing and the generated digital signature ciphertext are combined together to form a complete encrypted medical information package.

[0069] Further, over time, different encrypted medical information packages may have different usage frequencies and importance. For example, some patients' recent case information may be frequently used, while some historical case information has a lower usage frequency; at the same time, the information of some serious or complex cases may have higher importance. Through a pre-set time interval (such as monthly or quarterly), the system will re-evaluate these encrypted medical information packages. According to the evaluation results, the encrypted medical information packages are divided into different levels. For example, they can be divided into high frequency high importance, high frequency low importance, low frequency high importance, and low frequency low importance levels.

[0070] Further, for different levels of encrypted medical information packages, different storage media are selected. High-frequency information can be stored in storage media with good performance, such as solid state disks, to facilitate fast access; low-frequency information can be stored in low-cost storage media, such as tapes or large-capacity hard disks. In addition, according to the difference of storage media, the strength of encryption is adjusted. For encrypted medical information packages stored in high-security storage media, stronger encryption algorithms or longer key lengths can be used to improve security; for information stored in relatively secure storage media, relatively weak encryption can be used to balance security and performance costs.

[0071] Further, when a user initiates a system login request, the system will verify the user's identity information, and only after the user's identity and permission are verified, the user can access the encrypted medical information packages that the user has the right to access. According to the user's role and permission range, the system will retrieve the corresponding encrypted medical information package, and according to the stored information, use the corresponding decryption key and algorithm to decrypt the encrypted information, and provide the user with the required medical information.

[0072] Figure 2 A structure diagram of a dental anchorage cause remote diagnosis system provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the system includes a user terminal 100, a cloud server 200, and a storage server 300. Figure 2As shown, the tooth adhesion cause remote diagnosis system 200 includes an information acquisition unit 210, which receives user remote diagnosis login information, and acquires user condition information and historical diagnosis information according to the login information. A required historical case data screening unit 220 extracts tooth adhesion cause characteristics from the user condition information and the historical diagnosis information, and screens out required historical case data based on weight values corresponding to each tooth adhesion cause characteristic. A user tooth adhesion three-dimensional model construction unit 230 determines a tooth adhesion condition area based on the user condition information and the historical diagnosis information, matches key points in the tooth adhesion condition area, and constructs a user tooth adhesion three-dimensional model based on the matching result. A predicted tooth adhesion cause data acquisition unit 240 inputs the required historical case data and the user tooth adhesion three-dimensional model into a preset tooth adhesion cause prediction model, and obtains predicted tooth adhesion cause data. A treatment scheme matching unit 250 matches a corresponding tooth adhesion treatment scheme based on the required historical case data and the predicted tooth adhesion cause data. A data calling unit 260 encrypts and stores the predicted tooth adhesion cause data and the tooth adhesion treatment scheme, so as to call the encrypted data in the next time when the user remote diagnosis login information is received.

[0073] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0074] The above only describes the embodiments of the present application and is not used to limit the present application. The embodiments of the present application can be variously changed and modified by those skilled in the art. The modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for diagnosing a cause of tooth fixation disease remotely, characterized by, The method comprises: receiving user remote diagnosis login information, obtaining user condition information and historical diagnosis information according to the login information; extracting tooth fixation cause characteristics from the user condition information and the historical diagnosis information, screening required historical case data based on the weight values corresponding to each tooth fixation cause characteristic; based on the user condition information and the historical diagnosis information, determining the tooth fixation condition area, matching the key points in the tooth fixation condition area, and constructing a user tooth fixation three-dimensional model based on the matching result; inputting the required historical case data and the user tooth fixation three-dimensional model into a preset tooth fixation cause prediction model to obtain predicted tooth fixation cause data; based on the required historical case data and the predicted tooth fixation cause data, matching the corresponding tooth fixation treatment scheme; encrypting and storing the predicted tooth fixation cause data and the tooth fixation treatment scheme, so as to call the encrypted data when receiving user remote diagnosis login information next time; based on the user condition information and the historical diagnosis information, determining the tooth fixation condition area, matching the key points in the tooth fixation condition area, and constructing a user tooth fixation three-dimensional model based on the matching result, specifically comprising: based on the user condition information, constructing an initial tooth fixation three-dimensional model corresponding to the user; extracting the condition area from the initial tooth fixation three-dimensional model to obtain a condition area image, matching the condition area image with a condition image database, and determining the condition type corresponding to the condition area based on the matching result; based on an edge detection algorithm, identifying the pixel points of each condition area corresponding to each condition type, and determining the condition area area corresponding to each condition type based on the identified pixel point set; based on the user information, constructing a reference tooth three-dimensional model corresponding to the user; matching the key points of the reference tooth three-dimensional model and the initial tooth fixation three-dimensional model, adjusting the condition area area based on the matching result, and determining the user tooth fixation three-dimensional model based on the adjusted condition area area; the matching of the key points of the reference tooth three-dimensional model and the initial tooth fixation three-dimensional model based on the matching result, and the adjustment of the condition area area, specifically comprising: extracting the key points of the initial tooth fixation model and the reference tooth three-dimensional model through a preset key point extraction model; generating descriptors from the extracted key points, and matching the key points based on the similarity between the descriptors; based on the matched key points, determining the deformation field from the reference tooth three-dimensional model to the initial tooth fixation three-dimensional model through thin plate spline interpolation; based on the deformation field, mapping the condition area in the reference tooth three-dimensional model to the initial tooth fixation three-dimensional model, and adjusting the area of the condition area according to the deformation field; based on the required historical case data and the predicted tooth fixation cause data, matching the corresponding tooth fixation treatment scheme, specifically comprising: constructing a case library based on the required historical case data and treatment data corresponding to the required historical case data; performing a similarity matching between the predicted dental fixation cause data and the case library to obtain a first dental fixation treatment scheme set; dynamically adjusting a quantity threshold based on the number of treatment schemes in the first dental fixation treatment scheme set; obtaining historical case data of a user, and performing a secondary similarity matching in the first dental fixation treatment scheme set based on the historical case data and the quantity threshold to obtain a second dental fixation treatment scheme set; obtaining user basic information, constructing a personalized similarity model based on the user basic information, inputting the treatment schemes in the second dental fixation treatment scheme set into the personalized similarity model, and matching the corresponding dental fixation treatment schemes based on the output personalized similarity values; the encrypted storage of the predicted dental fixation cause data and the dental fixation treatment scheme for calling the encrypted data when receiving user remote diagnosis login information next time, specifically including: performing encryption processing on the predicted dental fixation cause data and the dental fixation treatment scheme through an SM3 encryption algorithm to obtain first digest information; generating digital signature ciphertext by encrypting the first digest information through an SM2 algorithm and a private key; generating an encrypted medical information package based on the encrypted predicted dental fixation cause data, the dental fixation treatment scheme, and the digital signature ciphertext; redetermining the usage frequency and importance of the encrypted medical information package after a preset interval, and dividing the encrypted medical information package into different levels based on the determination result; storing the encrypted medical information package of different levels to different storage media, and adjusting the encryption strength of the encrypted medical information package based on the difference of the storage media; verifying the identity and authority of the user when receiving a user system login request, and calling the corresponding encrypted medical information package when the verification is passed.

2. The method of claim 1, wherein the method comprises: the dental fixation cause feature extraction of the user condition information and the historical diagnosis information, and the screening of required historical case data based on the weight values corresponding to each dental fixation cause feature, specifically including: determining a plurality of dental fixation cause features based on the user condition information; sorting a plurality of the dental fixation cause features based on a pre-set dental fixation cause feature importance sequence, and sequentially screening historical case data meeting a feature similarity threshold in a database based on the sorting order to construct a plurality of historical case sets; sorting case data in a plurality of the historical case sets according to feature similarity, and assigning weights to each of the case data according to the sorting order; determining feature scores corresponding to each of the case data based on the weights corresponding to a plurality of the historical case sets and the weights corresponding to each of the case data; screening required historical case data according to the feature scores.

3. The method of claim 2, wherein the method further comprises: The method further comprises: According to the function: ； determining a feature score corresponding to each of the case data, wherein is a feature score; H is a set of historical case sets; h ij is a historical case set H i is the i-th data point in j is a set of weights for the historical case set wH n wH={wH 1 , wH 2 ,...,wH i } ; for each historical case set H i1 wh i2 ,wh im ,...,wh k F = { f 1 ,f 2 ,...,f F is a set of features; h ij is the value of the feature f l on the data point α is an adjustment factor for adjusting the degree to which the feature score is affected by the weights of the historical case set and the weights of the data point, and is in the range of [0, 1]; n is the number of historical case sets; m p is the number of data points in the historical case set H p .​​​​​ 4. The method of claim 1, wherein the method comprises: Before the method further comprises: Determine a first information entropy based on the preset dental adhesion cause prediction data set; Divide the preset dental adhesion cause prediction data set based on each candidate dental adhesion cause feature, and determine a second information entropy and an information gain corresponding to the divided preset dental adhesion cause prediction data set; Randomly extract data from the preset dental adhesion cause prediction data set, and determine a Gini coefficient based on the extraction result; Determine an optimal dental adhesion cause feature according to the first information entropy, the second information entropy, the information gain, and the Gini coefficient; From the root node, divide the preset training set data according to the preset division criterion and the optimal dental adhesion cause feature to obtain a plurality of subsets; each subset corresponds to a subnode. Divide each subnode according to the optimal dental adhesion cause feature corresponding to each subnode until a stop condition is met to construct the preset dental adhesion cause prediction model.

5. The method of claim 4, wherein the method further comprises: Before the method further comprises: Based on the user's personal physical information and the required historical case data, determine the dental adhesion feature pairs, and divide the dental adhesion feature pairs to obtain feature pairs with interaction and feature pairs without interaction; Linearly combine the feature pairs with interaction, and perform mathematical transformation processing on the feature pairs without interaction; Fuse the high-order features obtained after processing to obtain a first high-order feature set; Perform dimensionality reduction processing on the first high-order feature set by principal component analysis to obtain a second high-order feature set.

6. A dental fixation cause remote diagnosis system characterized by, The system comprises: An information acquisition unit receives user remote diagnosis login information, and acquires user condition information and historical diagnosis information according to the login information; A required historical case data screening unit extracts dental adhesion cause features from the user condition information and the historical diagnosis information, and screens required historical case data based on the weight values corresponding to each dental adhesion cause feature. The user tooth fixed connection three-dimensional model construction unit determines a tooth fixed connection disease area based on the user disease information and the historical diagnosis information, matches key points of the tooth fixed connection disease area, and constructs a user tooth fixed connection three-dimensional model based on a matching result; an initial tooth fixed connection three-dimensional model corresponding to the user is constructed based on user disease information; a disease area image is obtained by extracting a disease area from the initial tooth fixed connection three-dimensional model; the disease area image is matched with a disease image database, and a disease type corresponding to the disease area is determined based on a matching result; pixel points of the disease area corresponding to each disease type are identified based on an edge detection algorithm, and an area of the disease area corresponding to each disease type is determined based on an identified pixel point set; a reference tooth three-dimensional model corresponding to the user is constructed based on user information; key points of the reference tooth three-dimensional model and the initial tooth fixed connection three-dimensional model are matched, the area of the disease area is adjusted based on a matching result, and the user tooth fixed connection three-dimensional model is determined based on the adjusted area of the disease area; the key points of the reference tooth three-dimensional model and the initial tooth fixed connection three-dimensional model are matched, the area of the disease area is adjusted based on a matching result, and the adjustment specifically includes: key points of the initial tooth fixed connection model and the reference tooth three-dimensional model are extracted through a preset key point extraction model; the extracted key points are generated descriptors, and the key points are matched based on the similarity between the descriptors; based on the matched key points, a deformation field from the reference tooth three-dimensional model to the initial tooth fixed connection three-dimensional model is determined through thin plate spline interpolation; based on the deformation field, the disease area in the reference tooth three-dimensional model is mapped to the initial tooth fixed connection three-dimensional model, and the area of the disease area is adjusted according to the deformation field; The predicted tooth fixed connection cause data acquisition unit inputs the required historical case data and the user tooth fixed connection three-dimensional model into a preset tooth fixed connection cause prediction model to obtain predicted tooth fixed connection cause data; The treatment scheme matching unit matches a corresponding dental fixation treatment scheme based on the required historical case data and the predicted dental fixation cause data, constructs a case library based on the required historical case data and treatment data corresponding to the required historical case data, performs a first similarity matching on the predicted dental fixation cause data and the case library to obtain a first dental fixation treatment scheme set, dynamically adjusts a quantity threshold based on the number of treatment schemes in the first dental fixation treatment scheme set, obtains historical case data of a user, performs a second similarity matching on the first dental fixation treatment scheme set based on the historical case data and the quantity threshold to obtain a second dental fixation treatment scheme set, obtains user basic information, constructs a personalized similarity model based on the user basic information, inputs the treatment schemes in the second dental fixation treatment scheme set into the personalized similarity model, and matches a corresponding dental fixation treatment scheme based on an output personalized similarity value. The encrypted storage of the predicted dental fixation cause data and the dental fixation treatment scheme is used to call the encrypted data in the case of receiving user remote diagnosis login information next time, and specifically includes: the predicted dental fixation cause data and the dental fixation treatment scheme are encrypted by an SM3 encryption algorithm to obtain first digest information; the first digest information is encrypted by an SM2 algorithm and a private key to generate digital signature ciphertext; an encrypted medical information package is generated based on the encrypted predicted dental fixation cause data, the dental fixation treatment scheme, and the digital signature ciphertext; the use frequency and importance of the encrypted medical information package are determined again after an interval of a preset time length, and the encrypted medical information package is divided into different levels based on the determination result; the encrypted medical information packages of different levels are stored in different storage media, and the encryption strength of the encrypted medical information package is adjusted based on the difference of the storage media; when a user system login request is received, the identity and authority of the user are verified, and the corresponding encrypted medical information package is called in the case of passing the verification. The data calling unit encrypts and stores the predicted dental fixation cause data and the dental fixation treatment scheme to call the encrypted data in the case of receiving user remote diagnosis login information next time.

Images